iCreatAI News
Skip to content
Trending storyWatching

Vera Rubin makes its MLPerf debut, NVIDIA claims doubled training performance

2 reports2 sources1 days agoUpdated

Understand this story

AI overview

NVIDIA has published the results of the Vera Rubin architecture's first participation in MLPerf Training v6.1, claiming that Vera Rubin NVL72 achieves up to 2x the per-GPU training performance of GB300 NVL72 (Blackwell Ultra), and that it has submitted results across all training benchmarks. NVIDIA says its CUDA software stack was already fairly mature at its debut. These Vera Rubin results are currently provisional, pending validation by the MLCommons Association, and may change following peer review; the GB300 results used for comparison have been validated by the MLCommons Association. Therefore the "2x" is NVIDIA's claim based on provisional data, not a conclusion confirmed by a third party.

AI overview based on source reports · Updated 1 days ago

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 17
  1. NVIDIA Blog
    NVIDIA Sweeps MLPerf Training and Endpoints as Vera Rubin Debuts With Leading Performance

    In its MLPerf debut, NVIDIA's Vera Rubin platform swept every MLPerf Training v6.1 benchmark and delivered more than 10x generational gains in throughput per watt for agentic AI in its first MLPerf Endpoints submission. Vera Rubin NVL72 delivered up to 2x more performance per GPU than GB300 NVL72 and scaled from 256 to 1,024 GPUs with about 97% efficiency on DeepSeek-V3, while a provisional Kimi K3 result showed over 10x the throughput per watt of GB300 NVL72 at the same response speed. NVIDIA said Vera Rubin performance will keep climbing through continuous optimization of its CUDA-powered software stack.

  2. NVIDIA Technical BlogFeatured
    NVIDIA Vera Rubin NVL72 Achieves up to 2x Blackwell Ultra Performance in MLPerf Training v6.1

    MLPerf Training v6.1 marks the debut of the NVIDIA Vera Rubin architecture, with the Vera Rubin NVL72 platform delivering the fastest time in its first appearance. NVIDIA says these early results show its CUDA software stack is already highly mature, and the platform achieved up to 2x Blackwell Ultra performance.

Activity for this story

Current comparable activity
4
Peak comparable activity
10Nov 17 01:00
Change in the past 24 hours
-49%

Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.